Adam Khatib - A. Khatib

Adam Khatib

ROS, Perception and Control for Self-Driving Car Integration

ROS, Perception and Control for Self-Driving Car Integration

Final project for the Udacity Self-Driving Car Nanodegree: Programming a Real Self-Driving Car. Using ROS to integrate the planning, traffic light detection and vehicle controls.

Random Forest on Credit Card Approval Classification

Random Forest on Credit Card Approval Classification

This is an excerpt from my Kaggle notebook where I used a Random Forest classifier on credit card data (https://www.kaggle.com/datasets/rohitudageri/credit-card-details/data). Random Forest was extremely easy to use and offer great insights into the data relatively quickly. Exploring the Data The CSV had a

Vehicle Detection and Tracking in Highway Video Footage

Vehicle Detection and Tracking in Highway Video Footage

Detect vehicles and track them in a video! Using HOG features, an SVM and heatmap to find cars and track them in each frame of video.

Hill Model Simulation and Functional Electrical Stimulation

Hill Model Simulation and Functional Electrical Stimulation

While some have characterized the wrist as a second order system, the focus here is fitting a more complex fourth order model that accurately represents observed responses and muscle activity [1].

Neural Network Architecture for Detecting Traffic Signs

Neural Network Architecture for Detecting Traffic Signs

Design a convolutional neural network to classify traffic signs. Starting with the LeNet architecture and improving its generalization and accuracy.

Feedback Linearization - Its Performance and Limitations

Feedback Linearization - Its Performance and Limitations

The goal is to design a feedback control law that perfectly cancels the nonlinear term in the pendulum dynamics. For this simple example, the derivation is straightforward and the performance difference is easily observed.

Visualizing Key NFL Team Data on Win Conditions

Visualizing Key NFL Team Data on Win Conditions

Artificial Neural Networks and Machine Learning techniques have been used in the past to predict NFL game outcomes. Let's explore the data and find some correlations.

Color Generation in Morpho Wings and Possible Replication Methods

Color Generation in Morpho Wings and Possible Replication Methods

Structural colors have special properties that differ from colors produced by pigments. These include intensity patterns that change under different orientations and brilliant sparkling or glistening on the surface.

Improving Brain Computer Interface Prediction by Measuring Eye Position and Focus

Improving Brain Computer Interface Prediction by Measuring Eye Position and Focus

Eye tracking devices allow patients with locked-in syndrome to communicate by tracking eye movement through infrared sensing. Can we use this in conjunction with BCIs to improve accuracy?

Brain-Computer Interface: Motor Neuron Simulation

Brain-Computer Interface: Motor Neuron Simulation

Movements of the human body have been shown to correlate to neurons in the motor cortex of the brain and spinal cord.

Simple State Space Model of a Pendulum

This is the first post of a series that will build on simple pendulum dynamics to investigate different control laws and how model uncertainty affects the linear model approximation. Pendulum Model We will start by deriving the equations of motion for the simple pendulum shown below. The mass $m$ is

Testing Full State Feedback Controller on Nonlinear Pendulum Dynamics

We'll observe the response of a simple nonlinear pendulum by using a control law derived from linear analysis and test its performance.

Simple Inverted Pendulum: Linear State Feedback Control

We will start with that linear model and introduce a control $u$ proportional to the torque at the attachment point.